Progressive rectification network for irregular text recognition
文献类型：期刊论文
| 作者 | Gao, Yunze1,2 ; Chen, Yingying2; Wang, Jinqiao2; Lu, Hanqing2
|
| 刊名 | SCIENCE CHINA-INFORMATION SCIENCES
 |
| 出版日期 | 2020-01-14 |
| 卷号 | 63期号:2页码:14 |
| 关键词 | irregular text recognition progressive rectification iterative refinement |
| ISSN号 | 1674-733X |
| DOI | 10.1007/s11432-019-2710-7 |
| 通讯作者 | Chen, Yingying(yingying.chen@nlpr.ia.ac.cn) |
| 英文摘要 | Scene text recognition has received increasing attention in the research community. Text in the wild often possesses irregular arrangements, which typically include perspective, curved, and oriented texts. Most of the existing methods do not work well for irregular text, especially for severely distorted text. In this paper, we propose a novel progressive rectification network (PRN) for irregular scene text recognition. Our PRN progressively rectifies the irregular text to a front-horizontal view and further boosts the recognition performance. The distortions are removed step by step by leveraging the observation that the intermediate rectified result provides good guidance for subsequent higher quality rectification. Additionally, by decomposing the rectification process into multiple procedures, the difficulty of each step is considerably mitigated. First, we specifically perform a rough rectification, and then adopt iterative refinement to gradually achieve optimal rectification. Additionally, to avoid the boundary damage problem in direct iterations, we design an envelope-refinement structure to maintain the integrity of the text during the iterative process. Instead of the rectified images, the text line envelope is tracked and continually refined, which implicitly models the transformation information. Then, the original input image is consistently utilized for transformation based on the refined envelope. In this manner, the original character information is preserved until the final transformation. These designs lead to optimal rectification to boost the performance of succeeding recognition. Extensive experiments on eight challenging datasets demonstrate the superiority of our method, especially on irregular benchmarks. |
| 资助项目 | National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61806200] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000514581400001 |
| 出版者 | SCIENCE PRESS |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/38376]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
| 通讯作者 | Chen, Yingying |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Gao, Yunze,Chen, Yingying,Wang, Jinqiao,et al. Progressive rectification network for irregular text recognition[J]. SCIENCE CHINA-INFORMATION SCIENCES,2020,63(2):14. |
| APA | Gao, Yunze,Chen, Yingying,Wang, Jinqiao,&Lu, Hanqing.(2020).Progressive rectification network for irregular text recognition.SCIENCE CHINA-INFORMATION SCIENCES,63(2),14. |
| MLA | Gao, Yunze,et al."Progressive rectification network for irregular text recognition".SCIENCE CHINA-INFORMATION SCIENCES 63.2(2020):14. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。